Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5476. Min Range: -9.5476
Max Act: 9.5476. Min Act: -0.1700
Data Index: 2402229 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5476. Min Range: -9.5476
Max Act: 9.4851. Min Act: -0.1700
Data Index: 2227649 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5476. Min Range: -9.5476
Max Act: 9.2351. Min Act: -0.1700
Data Index: 5307320 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5476. Min Range: -9.5476
Max Act: 9.1726. Min Act: -0.1700
Data Index: 5728422 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5476. Min Range: -9.5476
Max Act: 9.1726. Min Act: -0.1700
Data Index: 160560 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5476. Min Range: -9.5476
Max Act: 9.1101. Min Act: -0.1700
Data Index: 2926391 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5476. Min Range: -9.5476
Max Act: 9.1726. Min Act: -0.1700
Data Index: 4035024 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5476. Min Range: -9.5476
Max Act: 9.1101. Min Act: -0.1700
Data Index: 6224619 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5476. Min Range: -9.5476
Max Act: 9.0476. Min Act: -0.1700
Data Index: 2807392 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5476. Min Range: -9.5476
Max Act: 9.0476. Min Act: -0.1700
Data Index: 6034418 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5476. Min Range: -9.5476
Max Act: 9.0476. Min Act: -0.1700
Data Index: 7877169 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5476. Min Range: -9.5476
Max Act: 8.9851. Min Act: -0.1700
Data Index: 662495 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5476. Min Range: -9.5476
Max Act: 8.9851. Min Act: -0.1700
Data Index: 5806611 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5476. Min Range: -9.5476
Max Act: 8.9851. Min Act: -0.1700
Data Index: 5046912 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5476. Min Range: -9.5476
Max Act: 8.9851. Min Act: -0.1700
Data Index: 645513 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5476. Min Range: -9.5476
Max Act: 8.9226. Min Act: -0.1700
Data Index: 6349191 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5476. Min Range: -9.5476
Max Act: 8.8601. Min Act: -0.1700
Data Index: 4849995 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5476. Min Range: -9.5476
Max Act: 8.8601. Min Act: -0.1700
Data Index: 5549058 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5476. Min Range: -9.5476
Max Act: 8.8601. Min Act: -0.1700
Data Index: 4276530 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5476. Min Range: -9.5476
Max Act: 8.8601. Min Act: -0.1700
Data Index: 6655058 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19